US9600713B2 - Identification and processing of facial wrinkles in a digital image - Google Patents
Identification and processing of facial wrinkles in a digital image Download PDFInfo
- Publication number
- US9600713B2 US9600713B2 US14/696,646 US201514696646A US9600713B2 US 9600713 B2 US9600713 B2 US 9600713B2 US 201514696646 A US201514696646 A US 201514696646A US 9600713 B2 US9600713 B2 US 9600713B2
- Authority
- US
- United States
- Prior art keywords
- facial
- digital image
- pixels
- regions
- input digital
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 230000037303 wrinkles Effects 0.000 title claims abstract description 99
- 230000001815 facial effect Effects 0.000 title claims abstract description 91
- 238000012545 processing Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000004590 computer program Methods 0.000 claims description 12
- 230000001419 dependent effect Effects 0.000 claims 1
- 230000004048 modification Effects 0.000 description 19
- 238000012986 modification Methods 0.000 description 19
- 238000004891 communication Methods 0.000 description 18
- 238000009499 grossing Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 8
- 230000003287 optical effect Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 239000002537 cosmetic Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 240000008168 Ficus benjamina Species 0.000 description 1
- 101100521334 Mus musculus Prom1 gene Proteins 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000013515 script Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000037331 wrinkle reduction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/162—Detection; Localisation; Normalisation using pixel segmentation or colour matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G06K9/00234—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04845—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
-
- G06K9/00248—
-
- G06T5/70—
-
- G06T7/0081—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Definitions
- Embodiments of the present invention relate generally to image processing, and more particularly to identification and processing of facial wrinkles in a digital image.
- Computer-based tools are available for providing users wish predictions, in the digital domain, about the results of an actual procedure that will affect the physical appearance of a subject.
- software is available for enabling a subject to visualize how they might look if they were to undergo a particular cosmetic procedure, in order to help the subject decide whether and how to proceed.
- One type of computer-based tool enables a user to apply basic global smoothing to an input digital image of the subject's face with a view to enabling the subject to see how the subject might look with, fewer wrinkles.
- Such a tool is known to be used in the publishing industry for removing facial blemishes from photographs prior to publication, rather than as a precursor to an actual physical procedure.
- U.S. Pat. No. 8,290,252 to Demirli et el. discloses a method and system for simulating the progress or worsening of facial skin features that contribute to the overall look and condition of the skin.
- Demirli et al. propose to use two close-up photographs of the lace: one captured with a digital camera in standard white light, and the other captured with the same camera in UV light. These images are processed to simulate the progress or worsening of the major skin features, such as hyperpigmented spots, wrinkles and small texture features.
- a computer-implemented method of processing an input digital image comprising forming a representation of the input digital Image as wavelet components; said for each of a plurality of facial regions in the input digital image: forming a reconstructed facial region based on a subset of the wavelet components; and identifying pixels associated with facial wrinkles in the facial region as pixels in the reconstructed facial region that differ from corresponding pixels in the facial region by a first threshold amount.
- a modified digital image is formed based on the input digital image and modified values of pixels identified as associated with facial wrinkles.
- the pixel value modifications are directed by a user.
- a non-transitory computer readable medium embodying a computer program executable on a computing system for processing an input digital image
- the computer program comprising: computer program code for forming a representation of the input digital image as wavelet components; and computer program code for, for each of a plurality of facial regions in the input digital image: forming a reconstructed facial region based on a subset of the wavelet components; and identifying pixels associated with facial wrinkles in the facial region as pixels in the reconstructed facial region that differ from corresponding pixels hi the facial region by a first threshold amount.
- pixel value modifications are directed by a user.
- a computing system comprising at least one processor executing instructions for processing an input digital image, the at least one processor configured therewith to form a representation of the input digital image as wavelet components and, for each of a plurality of facial regions in the input digital image, form a reconstructed facial region based on a subset of the wavelet components and identify pixels associated with facial wrinkles in the facial region as pixels in the reconstructed facial region that differ from corresponding pixels in the facial region by a first threshold amount.
- the at least one processor is further configured to form a modified digital image based on the input digital image and modified values of pixels identified as associated with facial wrinkles.
- the pixel value modifications are directed by a user.
- FIG. 1 is a schematic diagram of an exemplary computing system configured to implement embodiments of the invention
- FIG. 2 is a flowchart depicting steps in a computer-implemented method of processing a digital image, according to an embodiment
- FIG. 3 is a screenshot of a user interlace screen for enabling a user to select an input digital image
- FIG. 4 is a screenshot of a user interface screen for enabling a user to select the gender, ethnicity and age of the subject depicted in the selected input digital image;
- FIG. 5 is a screenshot of a user interface screen for enabling a user to manually identify the subject's facial regions using a facial mask
- FIG. 6 is a screenshot of a user interface screen for enabling a user to manually identify the subject's facial regions using control points;
- FIG. 7 depicts a number of images each illustrating a respective facial region that can be identified by a user
- FIG. 8 is a screenshot of a user interface screen providing user controls for controlling a degree of smoothing in finer wrinkle regions, a degree of wrinkle/shadow pixel colour changes in coarser wrinkle regions, and a degree of temple volumnization;
- FIG. 9 is a screenshot of the user interface screen of FIG. 8 being used to fine-tune the area of a particular facial region;
- FIG. 10 is a screenshot of a user interface screen showing side-by-side before and after comparisons thereby to enable a user to visually compare a modified digital image to the input digital image;
- FIG. 11 is a flowchart showing details of steps for the identification of modifiable pixels in a number of facial regions.
- computing system 1000 includes a bus 1010 or other communication mechanism for communicating information, and a processor 1018 coupled with the bus 1010 for processing the information.
- the computing system 1000 also includes a main memory 1004 , such as a random access memory (RAM) or other dynamic storage device (e.g., dynamic RAM (DRAM), static RAM (SRAM), and synchronous DRAM (SDRAM)), coupled to the bus 1010 for storing information and instructions to be executed by processor 1018 .
- RAM random access memory
- DRAM dynamic RAM
- SRAM static RAM
- SDRAM synchronous DRAM
- main memory 1004 may be used for storing temporary variables or other intermediate information during the execution of instructions by the processor 1018 .
- Processor 1018 may include memory structures such as registers for storing such temporary variables or other intermediate information during execution of instructions.
- the computing system 1000 further includes a read only memory (ROM) 1006 or other static storage device (e.g., programmable ROM (PROM), erasable PROM (EPROM), and electrically erasable PROM (EEPROM)) coupled to the bus 1010 for storing static information and instructions for the processor 1018 .
- ROM read only memory
- PROM programmable ROM
- EPROM erasable PROM
- EEPROM electrically erasable PROM
- the computing system 1000 also includes a disk controller 1008 coupled to the bus 1010 to control one or more storage devices for storing information and instructions, such as a magnetic hard disk 1022 , and a removable, media drive 1024 (e.g., floppy disk drive, read-only compact disc drive, read/write compact disc drive, compact disc jukebox, tape drive, and removable magneto-optical drive).
- the storage devices may be added to the computing system 1000 using an appropriate device interface (e.g., small computing system interface (SCSI), integrated device electronics (IDE), enhanced-IDE (E-IDE), direct memory access (DMA), or ultra-DMA).
- SCSI small computing system interface
- IDE integrated device electronics
- E-IDE enhanced-IDE
- DMA direct memory access
- ultra-DMA ultra-DMA
- the computing system 1000 may also include special purpose logic, devices (e.g., application specific integrated circuits (ASICs)) or configurable logic devices (e.g., simple programmable logic devices (SPLDs), complex programmable logic devices (CPLDs), and field programmable gate arrays (FPGAs)).
- ASICs application specific integrated circuits
- SPLDs simple programmable logic devices
- CPLDs complex programmable logic devices
- FPGAs field programmable gate arrays
- the computing system 1000 may also include a display controller 1002 coupled to the bus 1010 to control a display 1012 , such as a liquid crystal display (LCD) screen, for displaying information to a computer user.
- the computing system 1000 includes input devices, such as a keyboard 1014 and a pointing device 1016 , for interacting with a computer user and providing information to the processor 1018 .
- the pointing device 1016 may be a mouse, a trackball, or a pointing stick for communicating direction information and command selections to the processor 1018 and for controlling cursor movement on the display 1012 .
- a printer may provide printed listings of data stored and/or generated by the computing system 1000 .
- the computing system 1000 performs a portion or all of the processing steps in response to the processor 1018 executing one or more sequences of one- or more instructions contained, in a memory, such as the main memory 1004 .
- a memory such as the main memory 1004 .
- Such instructions may be read into the main memory 1004 from another computer readable medium, such as a hard disk 1022 or a removable media drive 1024 .
- processors in a multi-processing arrangement may also be employed to execute the sequences of instructions contained in main, memory 1004 .
- hard-wired circuitry may be used in place of or in combination with software instructions. Thus, embodiments are not limited to any specific combination of hardware circuitry and software.
- the computing system 1000 includes at least one computer readable medium or memory for holding instructions programmed according to the teachings of the invention and for containing data structures, tables, records, or other data described herein.
- Examples of computer readable media are compact discs, hard disks, floppy disks, tape, magneto-optical disks, PROMs (EPROM, EEPROM, flash EPROM), DRAM, SRAM, SDRAM, or any other magnetic medium, compact discs (e.g., CD-ROM), or any other optical medium, punch cards, paper tape, or other physical medium with patterns of holes, a carrier wave (described below), or any other medium from which a computer can read.
- Computer readable media Stored on any one or on a combination of computer readable media is software for controlling, the computing system 1000 , for driving a device or devices for implementing the invention, and for enabling the computing system 1000 to interact with a human user (e.g., by providing user interface screens and controls).
- software may include, but is trot limited to, device drivers, operating systems, development tools, and applications software.
- Such computer readable media further includes the computer program product of the present invention for performing ail or a portion (if processing is distributed) of the processing performed in implementing the invention.
- the computer code devices of the present invention may be any interpretable or executable code mechanism, including but trot limited to scripts, interpretable programs, dynamic link, libraries (DLLs), Java classes, and complete executable programs. Moreover, parts of the processing of the present invention may be distributed for better performance, reliability, and/or cost.
- a computer readable medium providing instructions to a processor 1018 may take many forms, including but not limited to, non-volatile media, volatile media, and transmission media.
- Non-volatile media includes, for example, optical, magnetic disks, and magneto-optical disks, such as the hard disk 1022 or the removable media drive 1024 .
- Volatile media includes dynamic memory, such as tire main, memory 1004 .
- Transmission media includes coaxial cables, copper wire and fiber optics, including the wires that make up the bus 1010 . Transmission media also may also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.
- Various forms of computer readable media may be involved in carrying out one or more sequences of one or more instructions to processor 1018 for execution.
- the instructions may initially be carried on a magnetic disk of a remote computer.
- the remote computer can load the instructions for implementing all or a portion of the present invention remotely into a dynamic memory and send the instructions over a telephone line using a modem.
- a modem local to the computing system 1000 may receive the data on the telephone line and use an infrared transmitter to convert the data to an infrared signal.
- An infrared detector coupled to the bus 1010 cart receive the data carried in the infrared signal and place the data on the bus 1010 .
- the bus 1010 carries the data to the main memory 1004 , from which the processor 1018 retrieves and executes the instructions.
- the instructions received by the main memory 1004 may optionally be stored on storage device 1022 or 1024 either before or after execution by processor 1018 .
- the computing system 1000 also includes a communication interface 1020 coupled to the bus 1010 .
- the communication interface 1020 provides a two-way data communication coupling to a network link that is connected to, for example, a local area network (LAN) 1500 , or to the communications network 2000 .
- the communication interface 1020 may be a network interface card to attach to any packet switched LAN.
- the communication interface 1020 may be an asymmetrical digital subscriber line (ADSL) card, an integrated services digital network (ISDN) card or a modem to provide a data communication connection to a corresponding type of communications line.
- Wireless links may also be implemented.
- the communication interface 1020 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.
- the network link typically provides data communication through one or more networks to other data devices.
- the network link may provide a connection to another computer through a local network 1500 (e.g., a LAN) or through equipment operated by a service provider, which provides communication services through a communications network 2000 .
- the local network 1500 and the communications network 2000 use, for example, electrical, electromagnetic, or optical signals that carry digital data streams, and die associated physical layer (e.g., CAT 5 cable, coaxial cable, optical fiber, etc).
- the signals through the various networks and the signals on the network link and through the communication interface 1020 which carry the digital data to and from the computing system 1000 , may be implemented in baseband signals, or carrier wave based signals.
- the baseband signals convey the digital data as unmodulated electrical pulses that are descriptive of a stream of digital data bits, where the term “bits” is to be construed broadly to mean symbol, where each symbol conveys at least one or more information bits.
- the digital data may also be used to modulate a carrier wave, such as with amplitude, phase and/or frequency shift keyed signals that are propagated over a conductive media, or transmitted as electromagnetic waves through a propagation medium.
- the digital data may be sent as unmodulated baseband data through a “wired” communication channel and/or sent within a predetermined frequency band, different than baseband, by modulating a carrier wave.
- the computing system 1000 can transmit and receive data, including program code, through the network(s) 1500 and 2000 , the network link and the communication interface 1020 .
- the network link may provide a connection through a LAN 1500 to a mobile device 1300 such as a personal digital assistant (PDA) laptop computer, or cellular telephone.
- PDA personal digital assistant
- computing system 1000 may be implemented in a tablet computer, thus not for example requiring a keyboard 1014 , or some other useful configuration.
- FIG. 2 is a flowchart depicting steps in method 90 , according to an embodiment.
- an input digital image in the form of a JPEG, BMP, TIFF, PNG or other suitable digital image format file, and basic characteristics of the subject of the input digital image, are received (step 100 ).
- FIGS. 3 and 4 are screenshots of a user interface screen 910 for respectively enabling a user to select an input digital image from a file system and to input tire gender 912 , ethnicity 914 and age 916 of the subject who is depicted in the input digital image.
- the user is provided with a text input field 918 within which the user can name a project.
- the project is stored in memory of computing system 1000 in one or more data structures and includes the input digital image, current pixel modification settings, sets of wrinkle/shadow pixels, the modified, digital image, user notes and other supporting data. The user, or another user, can retrieve the project at a later time using its name.
- FIGS. 5 and 6 are screenshots of the user interface screen 910 for enabling a user to manually identify the subject's facial regions.
- the sizes and positions of the facial regions and, as will be described, control points available to the user for the manual identification are informed partly by an underlying digital model of the subject selected based on the basic characteristics inputted by the user.
- the user is provided with an, image 920 of a Reference Face (on the left) and is able to re-position the image 920 so as to correspond in position and scale to the face in the input digital image 922 (on the right). As shown in FIG.
- FIG. 7 shows images illustrating various facial regions that can be determined using die mask and control points 924 a to 924 j . These include image 210 showing the Worry Lines Region, image 212 showing the Temple regions, image 214 showing the Glabellar Lines Region, image 216 showing the Nasolabial Folds regions, image 218 showing the Under Eve regions, image 220 showing the Oral Commissures regions, and image 222 showing the Perioral Lines Region.
- the input digital image is subjected to further processing.
- the further processing includes user-controllable smoothing of the respective regions using Gaussian blurring (step 300 ).
- the Gaussian, blurring uses a Gaussian filter in order to calculate a transformation to apply to pixels in die region, in this embodiment, for RGB (Red, Green, Blue) channels in an input digital image having a dimension of 512 ⁇ 215 pixels, the variance of the Gaussian Liter for the Periorbital Lines regions is 1.8, and the variance of the Gaussian filter for the Under Eye regions is 1.0. It will be understood that the user is able to control whether to apply any smoothing, on a region by region basis.
- the further processing includes identification of modifiable pixels in the regions (step 400 ), and then user-controllable modifications to the colour values of the identified modifiable pixels (step 500 ), each of which will be described in further detail below.
- the coarser wrinkle regions include the Nasolabial Folds regions, the Oral Commissures regions, the Worry Line Region, the Perioral Lines Region, and the Glabellar Lines regions.
- two different sets of modifiable pixels can be identified for some of these regions: a set of wrinkle pixels and a set of shadow pixels.
- the flexibility for defining the two different sets of pixels is provided for facial regions with features that tend to cause shadows.
- Providing the user with a set of wrinkle pixels or a set of shadow pixels enables the user to choose whether to modify identified shadow pixels in a region or whether to modify identified wrinkle pixels in the region. It will be understood that the user is also able to control whether or not to apply any modifications to the colour values of the identified modifiable pixels, on a region by region basis.
- the further processing includes user-controllable modifications to the colour values of the pixels in the Temple regions in order to depict different levels of any user-controlled volumnization of the subject's temples (step 600 ). It mil be understood that the user may choose not to apply any temple volumnization, on a region, by region basis.
- the selective modification of pixel values in the regions as described above are aggregated in real-time to form a modified digital image (step 700 ), which is continuously updated and displayed according to the modifications, and which may be saved (step 800 ).
- a modified digital image step 700
- the user is able to adjust the modifications to pixels in various regions and receive immediate visual feedback. Once the user is satisfied with the modifications, the user may save the modified digital image for future reference.
- FIG. 8 is a screenshot showing the user interface screen 910 displaying user controls for controlling the degree of smoothing in the finer wrinkle regions, the degree of wrinkle pixel colour, changes in the coarser wrinkle regions, and the degree of temple volumnization.
- the user can manipulate the user controls to control the appearance of the subject in a modified digital image 926 .
- a slider 928 is provided for controlling the degree of pixel colour changes in the Worry lines region
- left and right sliders 930 are provided for controlling the degree of smoothing for respective Periorbital Lines regions
- a slider 932 is provided for controlling the degree of pixel colour changes in the Glabellar Lines region
- left and right sliders 934 are provided for controlling the degree of smoothing in respective Under Eye regions
- a slider 936 is provided for controlling the degree of pixel colour changes in the Perioral.
- left and right sliders 938 are provided for controlling the degree of pixel colour changes in respective Nasolabial Fold regions
- left and right sliders 944 are provided for controlling the degree of pixel colour changes in respective Oral Commissures regions
- left and right sliders 950 are provided for controlling the degree of temple volumnization in the Temple regions.
- FIG. 9 is a screenshot showing the use of Area Control 946 for the Left Side Oral Commissure Region.
- this control the user is able to fine-tune the boundaries of the Left Side Oral Commissure region in order to enable fitting the detection of wrinkles and shadows, and their adjustments, around the mouth.
- the lute-tuning enables wrinkle reduction processing to more accurately address wrinkles around the mouth without impinging on the opening of the mouth itself.
- a shaded area 952 is shown overlying the modified digital image 926 to provide visual feedback to the user about the fine-tuning.
- Each Area Control provides control mainly over the shape of the region, the size of the region, and the size of the notch in the region that is to accommodate the side of the mouth or the side of the nose. Identification of wrinkle and shadow pixels, as well as their adjustments, are conducted only within the region.
- the Area Control 946 for each of the Left and Right Side Oral Commissure regions provides five (5) levels of fine-tuning
- the Area Control 940 for each, of the Left and Right Side Nasolabial Fold regions that provides three (3) levels of fine-tuning.
- FIG. 10 is a screenshot of a “before and after” comparison screen that enables a user to visualize the modified digital image 926 in comparison, with the input digital image 922 .
- the input digital image 922 is shown on the left as “Original” and the modified digital image 926 is shown on the right as “Smoothed”.
- FIG. 11 is a flowchart showing steps for the identification of modifiable pixels in step 400 , in further detail.
- nasolabial folds left and right
- oral commissures left and right
- worry lines perioral lines
- glabellar lines manifest themselves as deep wrinkles oriented in respective directions.
- nasolabial folds typically manifest themselves as diagonal lines
- oral commissures have complicated line patterns but also typically manifest themselves as deep lines extending downwardly from the mouth corner
- worry lines typically manifest themselves as horizontal lines
- perioral lines typically manifest themselves as lines in various directions
- glabellar lines typically manifest themselves as vertical lines.
- two-dimensional wavelets are employed as discrete-time filters for enabling detection of wrinkle pixels in accordance with the expected orientation of wrinkles in respective facial regions.
- c jk are wavelet-coefficients.
- a Discrete Wavelet Transform (“DWT”) is used to represent the input digital image as a set of scale components, referred to as wavelet coefficients, that each represent the information in the input digital image that corresponds to a respective frequency range.
- Derivative digital images, or regions thereof as in this embodiment can be reconstructed from, the wavelet components in various ways, for various purposes, using various combinations of the wavelet components. For example, if high-frequency components of the input digital image or region are not of interest for a reconstruction, only those wavelet components of the input digital image or region representing all but the high-frequency components are used to form a reconstructed digital, image or region. Where overall image smoothing and de-noising is desirable, for example, a reconstruction may be done without the highest-frequency components.
- wrinkle pixels may be detected by comparing pixel values in a region of an input digital image to corresponding pixel values in suitably reconstructed regions.
- the Daubechies 2 wavelet (db2) function is employed to determine wavelet components of the input digital image (step 410 ).
- db2 both Approximation Coefficients (A) and Detail Coefficients are determined.
- the Detail Coefficients at three (3) frequency levels are determined, with each level having three directions (horizontal (H), vertical (V), and diagonal (D)).
- the frequency range increases from level 1 to level 3.
- the input digital image may be represented as wavelet: components [A, H(1), V(1), D(1), H(2), V(2), D(2), H(3), V(3), D(3)].
- the user is able to select the Light Wrinkle or Deep Wrinkle radio box controls 942 and 948 .
- This provides the user with the ability to have the computing system 1000 either identify respective pixels attributable to wrinkles (where Deep Wrinkles is not selected at step 411 and/or step 417 ), or to identify respective pixels attributable to shadows (where Deep Wrinkles is selected at step 411 and/or step 417 ).
- the value of the HSV space V-channel of each pixel in the respective region is compared to a threshold value and, if the pixel value is below the threshold value, it is considered attributable to shadow. Otherwise, the pixel is considered not attributable to shadow.
- the threshold value is calculated adaptively based on the percentage of pixels in shadows and in the facial area in the region, in particular, in this embodiment the threshold amount is calculated as the amount of pixel value difference between pixels that would cause less than 75% of the pixels in the region to be shadow pixels and the rest of the pixels in the region to be non-shadow pixels.
- the particular percentage for the threshold in other embodiments may be somewhat less than or somewhat more than 40%, or may be some other percentage depending on the needs of the particular implementation.
- the regions' pixels in respective reconstructed regions are then compared with the corresponding regions' pixels in the input digital image regions to identify those pixels that are attributable to wrinkles in the input digital image.
- pixels have a Red channel, a Blue channel, and a Green channel
- only the Red channel values for pixels are compared.
- Those pixels whose Red channel values differ by a threshold amount, and not just any amount, are identified as wrinkle pixels.
- the threshold amount of pixel value difference is adapted to the contents of the facial region being processed, rather than fixed at a particular absolute amount. This provision enables the threshold amount to be established differently for different images taken under different lighting conditions, etc.
- a difference image is constructed from the pixels in the facial region and the pixels in the reconstructed facial region.
- the difference image will contain pixels of various values, since various differences may be present.
- the threshold amount: of pixel value difference to register a difference as representative of a wrinkle pixel in the facial region is calculated as the amount of difference in pixel value that would yield a particular percentage of wrinkle pixels in the difference image.
- the particular percentage is 40%.
- the threshold amount is calculated as the amount of pixel value difference between pixels that would cause more than 40% of the pixels in the difference image to be wrinkle pixels and the rest of the pixels in the difference image to be non-wrinkle pixels.
- the particular percentage is 60%, such that the threshold amount is calculated as the amount of pixel value difference between pixels that would cause more than 60% of the pixels in the difference image to be wrinkle pixels and the rest of the pixels in the difference image to be non-wrinkle pixels.
- the particular percentages for the threshold in other embodiments may be somewhat less than or somewhat more than 40%, somewhat less than or somewhat more than 60%, respectively, or may be some other ratio depending on the needs of the particular implementation.
- a reconstructed region is created using all but the D(1) and D(2) wavelet components (step 412 ), and the pixels in the reconstructed regions are compared to corresponding pixels in the Nasolabial Fold regions in the input digital image to identify wrinkle pixels in the Nasolabial Fold regions (step 414 ). It is these wrinkle pixels that are available to the user to modify as will be described.
- a reconstructed region is created using all but the H(1), H(2), D(1), D(2), V(1) and V(2) wavelet components (step 418 ), and the pixels in the reconstructed regions are compared to corresponding pixels in the Oral Commissure regions in the input digital image to identify wrinkle pixels in the Oral Commissures regions (step 420 ). These wrinkle pixels are also made available its die user to modify as will be described.
- a reconstructed region is created using all but the H(1) and H(2) wavelet components (step 424 ), and the pixels in the reconstructed region are compared to corresponding pixels in the Worry Lines Region in the Input digital image to identity wrinkle pixels in the Worry Lines Region (step 426 ). These wrinkle pixels are also made available to the user to modify as will be described.
- a reconstructed region is created using all but the H(1), H(2), D(1), D(2), V(1) and V(2) wavelet components (step 428 ), and the pixels in the reconstructed regions are compared to corresponding pixels in die Perioral Lines regions in the input digital image to identify wrinkle pixels in the Perioral Lines regions (step 430 ). These wrinkle pixels are also made available to the user to modify as will be described.
- a reconstructed region is created using all but the V(1) and V(2) wavelet components (step 432 ), and the pixels in the reconstructed region are compared to corresponding pixels in the Glabellar Lines Region in the input digital image to identify wrinkle pixels in the Glabellar Lines Region (step 434 ). These wrinkle pixels are also made available to the user to modify as will be described.
- pixel flooding begins with pixels at the boundaries of clusters of wrinkle/shadow pixels, so as to calculate modified pixel RGB channel values of pixels based on the value of RGB channels of pixels that are not wrinkle/shadow pixels.
- a modified channel value for a pixel at position (x, y) at the boundary of a cluster of wrinkle/shadow pixels in the input digital image having M rows and N columns of pixels, is calculated as in Equation 3 below:
- 2d+1 is the distance of boundary of tire neighbourhood
- Ns is the number of non wrinkle/shadow pixels in the neighbourhood.
- the user may select to identify and modify shadow pixels in a given region where Deep Wrinkles are observed, or to identify and modify the wrinkle pixels where light Wrinkles are observed.
- Oral Commissure regions each provide the user with the ability to modify either the shadow and wrinkle pixels in these regions, one or the other being modified depending upon whether the Deep Wrinkles radio box is selected or the light Wrinkles radio box is selected.
- the slider controls have a range of from zero (0) to one hundred and twenty (120).
- the corresponding displayed region in the “Smoothed” image is a combination of the input digital image and the modified wrinkle/shadow pixel channels' values for that region.
- the slider control for each region provides the user with the ability to control the amount of relative contribution to the displayed “Smoothed” image of the input digital image pixel channel values and the corresponding modified wrinkle/shadow pixels. For example, when the slider control for a particular region is at zero (0), what is displayed in that particular region is simply the original channel values of the input digital image.
- the slider control for a particular region is a forty (40), for example, what is displayed in that particular region is original non-wrinkle/non-shadow pixels along with wrinkle/shadow pixels whose channel values are equal to tire sum of 40/120 of the pixel channels' modified values and 80/120 of the pixel channels' original values.
- the slider control for the particular region is moved to 75, for example, what is displayed in that particular region is original non-wrinkle/non-shadow pixels along with wrinkle/shadow pixels whose channel values are equal to the sum of 75/120 of the pixel channels' modified values and 45/120 of the pixel channels' original values.
- the various selectable range of values for a slider are defined for each region such that, while each have a 0 to 120 range, the 100 value represents a change in pixel channels' values that is expected to represent the maximum aesthetically-pleasing change for the particular region. It is to be noted that the 100 value for a given region is merely a visual guidepost or initial recommendation for that region based, on the inventors' consideration of a large number of sample images and what, for a majority of the sample images, would represent an approximation of the maximum aesthetically-pleasing change in pixel channels' values.
- the 100 value does not indicate a 100 percent change in pixel value, or some other fixed, percentage or amount of change in the pixel value; it is merely a visual reference with no empirical relationship to the algorithms. It will be understood that the 100 value is merely a general approximation for assisting a user, and is not expected to exactly match, or actually represent the actual maximum aesthetically-pleasing change for any particular subject.
- the 120 value represents the maximum pixel change in a particular region that is available to die user. This additional range above 100 is provided in order to enable a user to manually hone in on an approximate maximum aesthetically-pleasing change (i.e, to go above 100 if desired for a particular subject ), and also to provide headroom to allow the user to depict for a given subject how an over-correction might appear.
- modifications to pixel values are directed by a user
- various modifications to the values of the wrinkle pixels may be done without requiring specific user input.
- the user may simply specify a proposed cosmetic procedure, after which wrinkle pixels corresponding to wrinkles that would be modified by such, a cosmetic procedure could be automatically modified and then, optionally, fine-tuned by a user.
- controls may be made available to a user to enable modifications of pixel values.
- a user may be provided with a single control that permits modifications to values of pixels in two regions at once, such as in both Oral Commissures regions.
- Red channels of pixels are compared during identification of wrinkle pixels
- the values of each of the Red, Blue and Green channels of a pixel may be compared to the Red, Blue and Green channels, respectively, of another pixel.
- modifications may be made to conduct comparisons of pixel values in one of the HSL (hue-saturation-lightness), HSV (hue-saturation-value), HSI (hue-saturation-intensity) colour spaces, or some other colour space.
Abstract
Description
ψj,k(t)=2j/2ψ(2j t−k) (1)
where
ψεL2(R); and
j, k εZ
where:
TABLE 1 | |||
WAVELET | WAVELET | ||
FACIAL | WRINKLE | CO-EFFS | CO-EFFS FOR |
REGION | PATTERN | TO REMOVE | RECONSTRUCTION |
Nasolabial | D | D(1), D(2) | [A, H(1), V(1), H(2), V(2), |
Folds regions | H(3), V(3), D(3)] | ||
Oral | H, V, D | H(1), H(2), V(1), | [A, H(3), V(3), D(3)] |
Commissures | V(2), D(1), D(2) | ||
legions | |||
Worry Lines | H | H(1), H(2) | [A, V(1), D(1), V(2), D(2), |
Region | H(3), V(3), D(3)] | ||
Perioral | H, V, D | H(1), H(2), V(1), | [A, H(3), V(3), D(3)] |
Lines regions | V(2), D(1), D(2) | ||
Glabellar | V | V(1), V(2) | [A, H(1), D(1), H(2), D(2), |
Lines Region | H(3), V(3), D(3)] | ||
where:
Claims (19)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/696,646 US9600713B2 (en) | 2015-04-27 | 2015-04-27 | Identification and processing of facial wrinkles in a digital image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/696,646 US9600713B2 (en) | 2015-04-27 | 2015-04-27 | Identification and processing of facial wrinkles in a digital image |
Publications (2)
Publication Number | Publication Date |
---|---|
US20160314342A1 US20160314342A1 (en) | 2016-10-27 |
US9600713B2 true US9600713B2 (en) | 2017-03-21 |
Family
ID=57146835
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US14/696,646 Expired - Fee Related US9600713B2 (en) | 2015-04-27 | 2015-04-27 | Identification and processing of facial wrinkles in a digital image |
Country Status (1)
Country | Link |
---|---|
US (1) | US9600713B2 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111767756A (en) * | 2019-03-29 | 2020-10-13 | 丽宝大数据股份有限公司 | Method for automatically detecting facial flaws |
CN114296622B (en) * | 2020-09-23 | 2023-08-08 | 北京达佳互联信息技术有限公司 | Image processing method, device, electronic equipment and storage medium |
CN115953313A (en) * | 2022-12-23 | 2023-04-11 | 百度在线网络技术(北京)有限公司 | Method, apparatus, device and storage medium for processing image |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6272231B1 (en) * | 1998-11-06 | 2001-08-07 | Eyematic Interfaces, Inc. | Wavelet-based facial motion capture for avatar animation |
US7336810B2 (en) * | 2003-06-11 | 2008-02-26 | KOSé CORPORATION | Skin evaluation method and image simulation method |
US20120133753A1 (en) * | 2010-11-26 | 2012-05-31 | Chuan-Yu Chang | System, device, method, and computer program product for facial defect analysis using angular facial image |
US8218896B2 (en) * | 2006-03-22 | 2012-07-10 | Samsung Electronics Co., Ltd. | Image display apparatus and method for correction chroma wrinkle |
US8290257B2 (en) | 2007-03-02 | 2012-10-16 | The Procter & Gamble Company | Method and apparatus for simulation of facial skin aging and de-aging |
US8391639B2 (en) | 2007-07-23 | 2013-03-05 | The Procter & Gamble Company | Method and apparatus for realistic simulation of wrinkle aging and de-aging |
-
2015
- 2015-04-27 US US14/696,646 patent/US9600713B2/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6272231B1 (en) * | 1998-11-06 | 2001-08-07 | Eyematic Interfaces, Inc. | Wavelet-based facial motion capture for avatar animation |
US7336810B2 (en) * | 2003-06-11 | 2008-02-26 | KOSé CORPORATION | Skin evaluation method and image simulation method |
US8218896B2 (en) * | 2006-03-22 | 2012-07-10 | Samsung Electronics Co., Ltd. | Image display apparatus and method for correction chroma wrinkle |
US8290257B2 (en) | 2007-03-02 | 2012-10-16 | The Procter & Gamble Company | Method and apparatus for simulation of facial skin aging and de-aging |
US8391639B2 (en) | 2007-07-23 | 2013-03-05 | The Procter & Gamble Company | Method and apparatus for realistic simulation of wrinkle aging and de-aging |
US20120133753A1 (en) * | 2010-11-26 | 2012-05-31 | Chuan-Yu Chang | System, device, method, and computer program product for facial defect analysis using angular facial image |
Non-Patent Citations (1)
Title |
---|
Zhang, et al. (Reconstruction of Human Face for Different Age Based on the Log-gabor Wavelet) , IEEE, 2008,pp. 354-357. * |
Also Published As
Publication number | Publication date |
---|---|
US20160314342A1 (en) | 2016-10-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Efficient single image dehazing and denoising: An efficient multi-scale correlated wavelet approach | |
Kaur et al. | Color image dehazing using gradient channel prior and guided l0 filter | |
Vocaturo et al. | Image pre-processing in computer vision systems for melanoma detection | |
US8867858B2 (en) | Method and system for generating an output image of increased pixel resolution from an input image | |
Natarajan et al. | Tumor detection using threshold operation in MRI brain images | |
US7983511B1 (en) | Methods and apparatus for noise reduction in digital images | |
US20140072242A1 (en) | Method for increasing image resolution | |
KR102410907B1 (en) | Image processing apparatus and image processing method thereof | |
KR102616700B1 (en) | Image processing apparatus and image processing method thereof | |
US9569684B2 (en) | Image enhancement using self-examples and external examples | |
KR101531966B1 (en) | Image Processing Device, Image Processing Program, Computer-Readable Recording Medium Storing Image Processing Program, and Image Processing Method | |
US9600713B2 (en) | Identification and processing of facial wrinkles in a digital image | |
Gupta et al. | Structure-aware adaptive bilateral texture filtering | |
Kaplan | Real-world image dehazing with improved joint enhancement and exposure fusion | |
Wei et al. | Joint contour filtering | |
Hmue et al. | Image enhancement and quality assessment methods in turbid water: A review article | |
Asghar et al. | Automatic enhancement of digital images using cubic Bézier curve and Fourier transformation | |
CN104168402A (en) | Method and device for video frame image defogging | |
Ashwini et al. | Image and video dehazing based on transmission estimation and refinement using Jaya algorithm | |
WO2022016326A1 (en) | Image processing method, electronic device, and computer-readable medium | |
WO2020241337A1 (en) | Image processing device | |
Yussof et al. | Enhancing moon crescent visibility using contrast-limited adaptive histogram equalization and bilateral filtering techniques | |
Singh et al. | Learning ramp transformation for single image super-resolution | |
Reddy et al. | Guided image filtering for image enhancement | |
Ghosh et al. | Image downscaling via co-occurrence learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: APRILAGE INC., CANADA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:ESTEY, RONALD;CHEN, FANG;ELLEFSON, CHRIS;REEL/FRAME:041195/0160 Effective date: 20150521 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
FEPP | Fee payment procedure |
Free format text: MAINTENANCE FEE REMINDER MAILED (ORIGINAL EVENT CODE: REM.); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY |
|
LAPS | Lapse for failure to pay maintenance fees |
Free format text: PATENT EXPIRED FOR FAILURE TO PAY MAINTENANCE FEES (ORIGINAL EVENT CODE: EXP.); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY |
|
STCH | Information on status: patent discontinuation |
Free format text: PATENT EXPIRED DUE TO NONPAYMENT OF MAINTENANCE FEES UNDER 37 CFR 1.362 |
|
FP | Lapsed due to failure to pay maintenance fee |
Effective date: 20210321 |